Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of restaurants or dining experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Carlton
    -0.15
    िह
    -0.14
    rab
    -0.14
     bound
    -0.14
     formation
    -0.14
    ála
    -0.13
    -placeholder
    -0.13
    ropp
    -0.13
     Release
    -0.13
     drives
    -0.13
    POSITIVE LOGITS
     serving
    0.40
     selling
    0.36
     serve
    0.35
    serve
    0.33
     serves
    0.31
     offering
    0.30
     Serving
    0.30
    -serving
    0.29
     sell
    0.29
     Serve
    0.29
    Act Density 0.164%

    No Known Activations